{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:L6JUGWGTDVNZIVC6E7AWKAPYAU","short_pith_number":"pith:L6JUGWGT","schema_version":"1.0","canonical_sha256":"5f934358d31d5b94545e27c16501f8053f7b7ec9ccbceeaec56611d5032d7a8a","source":{"kind":"arxiv","id":"2007.03047","version":3},"attestation_state":"computed","paper":{"title":"Leveraging Class Hierarchies with Metric-Guided Prototype Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Loic Landrieu, Vivien Sainte Fare Garnot","submitted_at":"2020-07-06T20:22:08Z","abstract_excerpt":"In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix, which defines a finite metric on the class set. In this paper, we propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network. Our method relies on jointly learning a feature-extracting network and a set of class prototypes whose relative arrangement in the embedding space follows an hierarchical metric. We show that this approach"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2007.03047","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-06T20:22:08Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"648c875b90ebece84578040eb955fc746cc549f6b43dd58910906bcf9e7e60bd","abstract_canon_sha256":"5cfa9d9eabf33b3c4c77a0373c598ffcdf85b08013aa9261de8ca86334b17070"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:48.118787Z","signature_b64":"9LeHI8PHMmedsm5EN5rhNPHIwB+KeGqUtdDMK8LZB7GLkgLPTc3x0xMzSGa6hcsjt2qM0uASmbgdEf6FU+NHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f934358d31d5b94545e27c16501f8053f7b7ec9ccbceeaec56611d5032d7a8a","last_reissued_at":"2026-07-05T03:35:48.118424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:48.118424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Class Hierarchies with Metric-Guided Prototype Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Loic Landrieu, Vivien Sainte Fare Garnot","submitted_at":"2020-07-06T20:22:08Z","abstract_excerpt":"In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix, which defines a finite metric on the class set. In this paper, we propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network. Our method relies on jointly learning a feature-extracting network and a set of class prototypes whose relative arrangement in the embedding space follows an hierarchical metric. We show that this approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03047","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.03047/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2007.03047","created_at":"2026-07-05T03:35:48.118484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03047v3","created_at":"2026-07-05T03:35:48.118484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03047","created_at":"2026-07-05T03:35:48.118484+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6JUGWGTDVNZ","created_at":"2026-07-05T03:35:48.118484+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6JUGWGTDVNZIVC6","created_at":"2026-07-05T03:35:48.118484+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6JUGWGT","created_at":"2026-07-05T03:35:48.118484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12885","citing_title":"$T^{3}S$: Think in Thermal Time for Generalizable Crop Mapping from Satellite Image Time Series","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU","json":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU.json","graph_json":"https://pith.science/api/pith-number/L6JUGWGTDVNZIVC6E7AWKAPYAU/graph.json","events_json":"https://pith.science/api/pith-number/L6JUGWGTDVNZIVC6E7AWKAPYAU/events.json","paper":"https://pith.science/paper/L6JUGWGT"},"agent_actions":{"view_html":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU","download_json":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU.json","view_paper":"https://pith.science/paper/L6JUGWGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03047&json=true","fetch_graph":"https://pith.science/api/pith-number/L6JUGWGTDVNZIVC6E7AWKAPYAU/graph.json","fetch_events":"https://pith.science/api/pith-number/L6JUGWGTDVNZIVC6E7AWKAPYAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU/action/storage_attestation","attest_author":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU/action/author_attestation","sign_citation":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU/action/citation_signature","submit_replication":"https://pith.science/pith/L6JUGWGTDVNZIVC6E7AWKAPYAU/action/replication_record"}},"created_at":"2026-07-05T03:35:48.118484+00:00","updated_at":"2026-07-05T03:35:48.118484+00:00"}